Remove an autoload singleton from the project settings.
AI agents call remove_autoload to permanently remove resources in Godot Mcp Pilot — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing an autoload singleton from project settings is a destructive operation that modifies project configuration in a way that can break dependent systems. Autoloads are globally accessible singletons referenced throughout the project; removing one can cause cascading failures in scripts that depend on it, and the removal from project settings may not be easily reversible without version control.
From the tool's definition Remove an autoload singleton from the project settings
Attacks that exploit this kind of access
Remove an autoload singleton from the project settings. It is categorised as a Destructive tool in the Godot Mcp Pilot MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Godot Mcp Pilot MCP server in PolicyLayer and add a rule for remove_autoload: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Godot Mcp Pilot. Nothing to install.
remove_autoload is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_autoload rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for remove_autoload. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
remove_autoload is provided by the Godot Mcp Pilot MCP server (pushks18/godot-mcp-pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →